Statut  Confirmé 
Série  LPTMS 
Domaines  physics 
Date  Mardi 19 Juin 2018 
Heure  11:00 
Institut  LPTMS 
Salle  LPTMS, salle 201, 2ème étage, bâtiment 100, Campus d'Orsay 
Nom de l'orateur  Decelle 
Prenom de l'orateur  Aurélien 
Addresse email de l'orateur  
Institution de l'orateur  Laboratoire de recherche informatique, Université ParisSud 
Titre  Spectral learning of Restricted Boltzmann Machines 
Résumé  In this presentation I will expose our recent results on the Restricted Boltzman Machine (RBM). The RBM is a generative model very similar to the Ising model, it is composed of both visible and hidden binary variables, and traditionally used in the context of machine learning. In this context, the goal is to infer the parameters of the RBM such that it reproduces correctly a dataset’s distribution. Although they have been widely used in computer science, the phase diagram of this model is not known precisely in the context of learning. In particular, it is not known how the parameters influence the learning, and what exactly is learned within the parameters of the model. After an introduction to some aspects of Machine learning, I will expose our work, showing how the SVD of the data governs the first phase of the learning and how this decomposition helps to understand the dynamics and the equilibrium properties of the model. Réf: Aurélien Decelle, Giancarlo Fissore and Cyril Furtlehner, Spectral dynamics of learning in restricted Boltzmann machines, EuroPhys. Lett. 119, 60001 (2017) Aurélien Decelle, Giancarlo Fissore and Cyril Furtlehner, Thermodynamics of Restricted Boltzmann Machines and related learning dynamics, preprint condmat arXiv:1803.01960 (2018). 
Numéro de preprint arXiv  
Commentaires  
Fichiers attachés 
Pour obtenir l' affiche de ce séminaire : [ Postscript  PDF ]

[ English version ] 